{"id":"W4390116162","doi":"10.1016/j.cviu.2023.103906","title":"Learning feature contexts by transformer and CNN hybrid deep network for weakly supervised person search","year":2023,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Heilongjiang Province; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Discriminative model; Transformer; Feature (linguistics); Machine learning; Feature learning; Pattern recognition (psychology); Feature extraction; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001204899,0.0002294962,0.0003079787,0.000153179,0.0007471257,0.00077783,0.0002590092,0.00007713548,0.00000452462],"category_scores_gemma":[0.00002789109,0.0002019899,0.0000907398,0.0003976422,0.00009678303,0.0006368303,0.0001047719,0.0002876465,0.000005523633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005216999,"about_ca_system_score_gemma":0.00002120822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005258177,"about_ca_topic_score_gemma":0.000003398142,"domain_scores_codex":[0.9982277,0.000198168,0.0001713952,0.0006020041,0.000236506,0.0005642204],"domain_scores_gemma":[0.9988906,0.0006351975,0.00004373274,0.0001896987,0.00006758618,0.0001731508],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001683456,0.00004900231,0.002390327,0.0003713144,0.0001322501,0.00008777965,0.00747255,0.0005600078,0.01108001,0.009244024,0.07266663,0.8957778],"study_design_scores_gemma":[0.00174651,0.0006337033,0.001747437,0.0001755861,0.00001224443,0.000045383,0.0006774056,0.9854482,0.0005885608,0.003926651,0.004560705,0.0004375725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01466276,0.0006623596,0.9812235,0.002259344,0.0004163461,0.0002984025,0.000005013002,0.000289586,0.0001826823],"genre_scores_gemma":[0.8360845,0.0005329703,0.1621008,0.0005543444,0.0003031609,0.00001066471,0.00004201721,0.00004117285,0.0003303426],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9848883,"threshold_uncertainty_score":0.8236909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04349798754286054,"score_gpt":0.3042416187592012,"score_spread":0.2607436312163407,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}